myeclipse下搭建hadoop2.7.3开发环境

沙漏无语

于 2018-12-21 10:43:33 发布

阅读量218

点赞数

分类专栏：大数据技术开发

本文链接：https://blog.csdn.net/estelle_belle/article/details/85158279

版权

大数据技术开发专栏收录该内容

17 篇文章 1 订阅

订阅专栏

一下载并编译 hadoop-eclipse-plugin-2.7.3.jar

二将hadoop-eclipse-plugin-2.7.3.jar放到myeclipse的安装目录下的plugins目录下，并重启myeclipse

　　在windows->preferences下可看见hadoop Map/Reduce界面，路径选择你WINDOWS下的hadoop解压后的路径。

三选择Windows->show view->others下的MapReduce Locations

四新建一个配置配置如下

host为你的远程hadoop待连接的主机IP地址

Port:8020对应mapred-site.xml下的jobtracher地址

Port:8020对应core-site.xml下的fs.default.name的端口

user name 填你windows的用户名；

修改Advanced parameters下的参数

值对应 core-site.xml下的hadoop.tmp.dir参数

修改hdfs-site.xml下的dfs.permissions参数，允许连接，免权限检测

四保存配置参数并重启myeclipse,可以看见如下的文件结构说明配置连接成功。

五下载hadoop.ll和winutils.exe 到windows的hadoop/bin目录下

并将hadoop.dll添加到windows->system32目录下

五环境测试

　　新建项目：File-->New-->Other-->Map/Reduce Project ,项目名可以随便取

　　它会自动添加依赖包，如下：

新建如下文件：

编写实现代码，与官方例子为例

package com.duking.hadoop;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{

private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}

public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();

public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();

String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println(otherArgs.length);
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}